Power system distributed dynamic state prediction

The security of the power system can be enhanced with the prediction of the dynamic state variables. To increase the security, a distributed predictor is developed based on the Elman Recurrent Neural Network (ERNN) in this study. To develop a scalable distributed predictor, the whole network is divided in a number of ERNNs. They take the current and the previous actual states from its own and its neighbors to predict the near future values of the states. The concept is inspired from the Cellular Computational Network (CCN) framework. Each ERNN is a cell in the CCN framework. Through simulation, the effectiveness of the proposed network is shown for a single step and a multi-step predictor and their accuracies are analyzed for IEEE 68-bus system.